Research on human emotions has started to address psychological aspects of human nature and has advanced to the point of designing various models that represent them quantitatively and systematically. Based on the fin...Research on human emotions has started to address psychological aspects of human nature and has advanced to the point of designing various models that represent them quantitatively and systematically. Based on the findings, a method is suggested for emotional space formation and emotional inference that enhance the quality and maximize the reality of emotion-based personalized services. In consideration of the subjective tendencies of individuals, AHP was adopted for the quantitative evaluation of human emotions, based on which an emotional space remodeling method is suggested in reference to the emotional model of Thayer and Plutchik, which takes into account personal emotions. In addition, Sugeno fuzzy inference, fuzzy measures, and Choquet integral were adopted for emotional inference in the remodeled personalized emotional space model. Its performance was evaluated through an experiment. Fourteen cases were analyzed with 4.0 and higher evaluation value of emotions inferred, for the evaluation of emotional similarity, through the case studies of 17 kinds of emotional inference methods. Matching results per inference method in ten cases accounting for 71% are confirmed. It is also found that the remaining two cases are inferred as adjoining emotion in the same section. In this manner, the similarity of inference results is verified.展开更多
The stock market is a vital component of the broader financial system,with its dynamics closely linked to economic growth.The challenges associated with analyzing and forecasting stock prices have persisted since the ...The stock market is a vital component of the broader financial system,with its dynamics closely linked to economic growth.The challenges associated with analyzing and forecasting stock prices have persisted since the inception of financial markets.By examining historical transaction data,latent opportunities for profit can be uncovered,providing valuable insights for both institutional and individual investors to make more informed decisions.This study focuses on analyzing historical transaction data from four banks to predict closing price trends.Various models,including decision trees,random forests,and Long Short-Term Memory(LSTM)networks,are employed to forecast stock price movements.Historical stock transaction data serves as the input for training these models,which are then used to predict upward or downward stock price trends.The study’s empirical results indicate that these methods are effective to a degree in predicting stock price movements.The LSTM-based deep neural network model,in particular,demonstrates a commendable level of predictive accuracy.This conclusion is reached following a thorough evaluation of model performance,highlighting the potential of LSTM models in stock market forecasting.The findings offer significant implications for advancing financial forecasting approaches,thereby improving the decision-making capabilities of investors and financial institutions.展开更多
Objective To observe the effects of repeated subconvulsive electrical stimuli to the hippocampus on the emotional behavior and spatial learning and memory ability in rats.Methods One hundred and eight male Wistar rats...Objective To observe the effects of repeated subconvulsive electrical stimuli to the hippocampus on the emotional behavior and spatial learning and memory ability in rats.Methods One hundred and eight male Wistar rats were randomized into 3 groups. Animals in group SE (n = 42) were given subconvulsive electrical stimulation to the hippocampus through a constant pulsating current of 100 μA with an intratrain frequency of 25 Hz, pulse duration of 1 millisecond, train duration of 10 seconds and interstimulus interval of 7 minutes, 8 times a day, for 5 days. In the electrode control group or CE group (n = 33), animals were implanted with an electrode in the hippocampus, but were not stimulated. Group NC (n =33) animals received no electrode or any stimulation. The emotional behavior of experimental rats was examined by activity in an unfamiliar open field and resistance to capture from the open field, while the spatial learning and memory ability was measured during training in a Morris water maze.Results The stimulated rats tested 1 month after the last round of stimulation displayed substantial decreases in open field activity (scale: 10. 4±2. 3, P<0. 05) and increases in resistance to capture (scale: 2. 85±0. 56, P < 0. 01 ). The amount of time for rats in group SE to find the platform (latency) as a measurement for spatial bias was prolonged (29±7) seconds after 15 trials in the water maze, P<0. 05). The experimental rats swam aimlessly in all four pool quadrants during the probe trial in the Morris water maze.Conclusions Following repeated subconvulsive electrical stimuli to the hippocampus, rats displayed long-lasting significant abnormalities in emotional behavior, increased anxiety and defensiveness, enhanced ease to and delayed habituation to startlement, transitory spatial learning and memory disorder, which parallels many of the symptoms in posttraumatic stress disorder patients.展开更多
In the paper, a general framework for large scale modeling of macroeconomic and financial time series is introduced. The proposed approach is characterized by simplicity of implementation, performing well independentl...In the paper, a general framework for large scale modeling of macroeconomic and financial time series is introduced. The proposed approach is characterized by simplicity of implementation, performing well independently of persistence and heteroskedasticity properties, accounting for common deterministic and stochastic factors. Monte Carlo results strongly support the proposed methodology, validating its use also for relatively small cross-sectional and temporal samples.展开更多
Neurons are believed to be the brain computational engines of the brain. A recent discovery in neurophysiology reveals that interneurons can slowly integrate spiking, share the output across a coupled network of axons...Neurons are believed to be the brain computational engines of the brain. A recent discovery in neurophysiology reveals that interneurons can slowly integrate spiking, share the output across a coupled network of axons and respond with persistent firing even in the absence of input to the soma or dendrites, which has not been understood and could be very important for exploring the mechanism of human cognition. The conventional models are incapable of simulating the important newly-discovered phenomenon of persistent firing induced by axonal slow integration. In this paper, we propose a computationally efficient model of neurons through modeling the axon as a slow leaky integrator, which captures almost all-known neural behaviors. The model controls the switching of axonal firing dynamics between passive conduction mode and persistent firing mode. The interplay between the axonal integrated potential and its multiple thresholds in axon precisely determines the persistent firing dynamics of neurons. We also present a persistent firing polychronous spiking network which exhibits asynchronous dynamics indicating that this computationally efficient model is not only bio-plausible, but also suitable for large scale spiking network simulations. The implications of this network and the analog circuit design for exploring the relationship between working memory and persistent firing enable developing a spiking network-based memory and bio-inspired computer systems.展开更多
交通流量因受周期性特征、突发状况等多重因素影响,现有模型的预测精度无法满足实际要求.对此,本文提出了基于误差补偿的多模态协同交通流预测模型(Multimodal Collaborative traffic flow prediction model based on Error Compensatio...交通流量因受周期性特征、突发状况等多重因素影响,现有模型的预测精度无法满足实际要求.对此,本文提出了基于误差补偿的多模态协同交通流预测模型(Multimodal Collaborative traffic flow prediction model based on Error Compensation,MCEC).针对传统预测模型不能兼顾时间序列和协变量的问题,提出基于小波分析的特征拓展方法,该方法引入聚类算法得到节假日标签特征,将拥堵指数、交通事故图、天气信息作为拓展特征,对特征进行多尺度分解.在训练阶段,为达到充分学习各部分数据、最优匹配模型的效果,采用差分整合移动平均自回归模型(Autoreg Ressive Integrated Moving Average Model,ARIMA)、长短期记忆神经网络(Long Short-Term Memory network,LSTM)、限制动态时间规整技术(Dynamic Time Warping,DTW)以及自注意力机制(Self-Attention),设计了多模态协同模型训练.在误差补偿阶段,将得到的相应过程值输入基于支持向量机回归(Support Vector Regression,SVR)的误差补偿模块,对各分量的误差进行学习、补偿,并重构得到预测结果.使用公开的高速公路数据集对MCEC进行验证,在多个时间间隔下对比实验结果表明,MCEC在交通流量预测中的平均绝对百分比误差(Mean Absolute Percentage Error,MAPE)达到17.02%,比LSTM-SVR、ConvLSTM(Convolutional Long Short-Term Memory network)、ST-GCN(Spatial Temporal Graph Convolutional Networks)、MFFB(Multi-stream Feature Fusion Block)、Transformer等预测模型具有更高的预测精度,MCEC模型具有较好的有效性与合理性.展开更多
Severe fever with thrombocytopenia syndrome (SFTS) is an emerging infectious disease caused by the SFTS virus (SFTSV). Predicting the incidence of this disease in advance is crucial for policymakers to develop prevent...Severe fever with thrombocytopenia syndrome (SFTS) is an emerging infectious disease caused by the SFTS virus (SFTSV). Predicting the incidence of this disease in advance is crucial for policymakers to develop prevention and control strategies. In this study, we utilized historical incidence data of SFTS (2013–2020) in Shandong Province, China to establish three univariate prediction models based on two time-series forecasting algorithms Autoregressive Integrated Moving Average (ARIMA) and Prophet, as well as a special type of recurrent neural network Long Short-Term Memory (LSTM) algorithm. We then evaluated and compared the performance of these models. All three models demonstrated good predictive capabilities for SFTS cases, with the predicted results closely aligning with the actual cases. Among the models, the LSTM model exhibited the best fitting and prediction performance. It achieved the lowest values for mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE). The number of SFTS cases in the subsequent 5 years in this area were also generated using this model. The LSTM model, being simple and practical, provides valuable information and data for assessing the potential risk of SFTS in advance. This information is crucial for the development of early warning systems and the formulation of effective prevention and control measures for SFTS.展开更多
针对中文儿童语音情感识别的准确性问题,提出了一种结合深度卷积神经网络(Deep Convolutional Neural Network,DPCNN)与堆叠长短时记忆(Stacked Long Short Term Memory,SLSTM)网络的融合模型,旨在提高中文儿童语音情感识别的准确性。通...针对中文儿童语音情感识别的准确性问题,提出了一种结合深度卷积神经网络(Deep Convolutional Neural Network,DPCNN)与堆叠长短时记忆(Stacked Long Short Term Memory,SLSTM)网络的融合模型,旨在提高中文儿童语音情感识别的准确性。通过DPCNN对语音信号中的长距离依赖关系进行提取,再利用SLSTM捕捉情感相关的序列依赖信息,最终通过softmax分类器实现情感状态的判别。实验结果显示,基于DPCNN-SLSTM的模型在中文儿童语音数据集上的情感识别准确率达到了92%,显著优于CNN、LSTM和CNN-LSTM模型。研究结果对于推动儿童语音情感识别技术的发展具有重要意义。展开更多
基金Project(2012R1A1A2042625) supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education
文摘Research on human emotions has started to address psychological aspects of human nature and has advanced to the point of designing various models that represent them quantitatively and systematically. Based on the findings, a method is suggested for emotional space formation and emotional inference that enhance the quality and maximize the reality of emotion-based personalized services. In consideration of the subjective tendencies of individuals, AHP was adopted for the quantitative evaluation of human emotions, based on which an emotional space remodeling method is suggested in reference to the emotional model of Thayer and Plutchik, which takes into account personal emotions. In addition, Sugeno fuzzy inference, fuzzy measures, and Choquet integral were adopted for emotional inference in the remodeled personalized emotional space model. Its performance was evaluated through an experiment. Fourteen cases were analyzed with 4.0 and higher evaluation value of emotions inferred, for the evaluation of emotional similarity, through the case studies of 17 kinds of emotional inference methods. Matching results per inference method in ten cases accounting for 71% are confirmed. It is also found that the remaining two cases are inferred as adjoining emotion in the same section. In this manner, the similarity of inference results is verified.
文摘The stock market is a vital component of the broader financial system,with its dynamics closely linked to economic growth.The challenges associated with analyzing and forecasting stock prices have persisted since the inception of financial markets.By examining historical transaction data,latent opportunities for profit can be uncovered,providing valuable insights for both institutional and individual investors to make more informed decisions.This study focuses on analyzing historical transaction data from four banks to predict closing price trends.Various models,including decision trees,random forests,and Long Short-Term Memory(LSTM)networks,are employed to forecast stock price movements.Historical stock transaction data serves as the input for training these models,which are then used to predict upward or downward stock price trends.The study’s empirical results indicate that these methods are effective to a degree in predicting stock price movements.The LSTM-based deep neural network model,in particular,demonstrates a commendable level of predictive accuracy.This conclusion is reached following a thorough evaluation of model performance,highlighting the potential of LSTM models in stock market forecasting.The findings offer significant implications for advancing financial forecasting approaches,thereby improving the decision-making capabilities of investors and financial institutions.
基金This study was supported by grants from the National Natural Science Foundation of China (No. 39870284) and the Tenth Five-Year Plan for Medical Projects of PLA (No. 01L028).
文摘Objective To observe the effects of repeated subconvulsive electrical stimuli to the hippocampus on the emotional behavior and spatial learning and memory ability in rats.Methods One hundred and eight male Wistar rats were randomized into 3 groups. Animals in group SE (n = 42) were given subconvulsive electrical stimulation to the hippocampus through a constant pulsating current of 100 μA with an intratrain frequency of 25 Hz, pulse duration of 1 millisecond, train duration of 10 seconds and interstimulus interval of 7 minutes, 8 times a day, for 5 days. In the electrode control group or CE group (n = 33), animals were implanted with an electrode in the hippocampus, but were not stimulated. Group NC (n =33) animals received no electrode or any stimulation. The emotional behavior of experimental rats was examined by activity in an unfamiliar open field and resistance to capture from the open field, while the spatial learning and memory ability was measured during training in a Morris water maze.Results The stimulated rats tested 1 month after the last round of stimulation displayed substantial decreases in open field activity (scale: 10. 4±2. 3, P<0. 05) and increases in resistance to capture (scale: 2. 85±0. 56, P < 0. 01 ). The amount of time for rats in group SE to find the platform (latency) as a measurement for spatial bias was prolonged (29±7) seconds after 15 trials in the water maze, P<0. 05). The experimental rats swam aimlessly in all four pool quadrants during the probe trial in the Morris water maze.Conclusions Following repeated subconvulsive electrical stimuli to the hippocampus, rats displayed long-lasting significant abnormalities in emotional behavior, increased anxiety and defensiveness, enhanced ease to and delayed habituation to startlement, transitory spatial learning and memory disorder, which parallels many of the symptoms in posttraumatic stress disorder patients.
文摘In the paper, a general framework for large scale modeling of macroeconomic and financial time series is introduced. The proposed approach is characterized by simplicity of implementation, performing well independently of persistence and heteroskedasticity properties, accounting for common deterministic and stochastic factors. Monte Carlo results strongly support the proposed methodology, validating its use also for relatively small cross-sectional and temporal samples.
文摘Neurons are believed to be the brain computational engines of the brain. A recent discovery in neurophysiology reveals that interneurons can slowly integrate spiking, share the output across a coupled network of axons and respond with persistent firing even in the absence of input to the soma or dendrites, which has not been understood and could be very important for exploring the mechanism of human cognition. The conventional models are incapable of simulating the important newly-discovered phenomenon of persistent firing induced by axonal slow integration. In this paper, we propose a computationally efficient model of neurons through modeling the axon as a slow leaky integrator, which captures almost all-known neural behaviors. The model controls the switching of axonal firing dynamics between passive conduction mode and persistent firing mode. The interplay between the axonal integrated potential and its multiple thresholds in axon precisely determines the persistent firing dynamics of neurons. We also present a persistent firing polychronous spiking network which exhibits asynchronous dynamics indicating that this computationally efficient model is not only bio-plausible, but also suitable for large scale spiking network simulations. The implications of this network and the analog circuit design for exploring the relationship between working memory and persistent firing enable developing a spiking network-based memory and bio-inspired computer systems.
基金funded by Medical Science and Technology Projects,China(JK2023GK002,JK2023GK003,and JK2023GK004).
文摘Severe fever with thrombocytopenia syndrome (SFTS) is an emerging infectious disease caused by the SFTS virus (SFTSV). Predicting the incidence of this disease in advance is crucial for policymakers to develop prevention and control strategies. In this study, we utilized historical incidence data of SFTS (2013–2020) in Shandong Province, China to establish three univariate prediction models based on two time-series forecasting algorithms Autoregressive Integrated Moving Average (ARIMA) and Prophet, as well as a special type of recurrent neural network Long Short-Term Memory (LSTM) algorithm. We then evaluated and compared the performance of these models. All three models demonstrated good predictive capabilities for SFTS cases, with the predicted results closely aligning with the actual cases. Among the models, the LSTM model exhibited the best fitting and prediction performance. It achieved the lowest values for mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE). The number of SFTS cases in the subsequent 5 years in this area were also generated using this model. The LSTM model, being simple and practical, provides valuable information and data for assessing the potential risk of SFTS in advance. This information is crucial for the development of early warning systems and the formulation of effective prevention and control measures for SFTS.
文摘针对中文儿童语音情感识别的准确性问题,提出了一种结合深度卷积神经网络(Deep Convolutional Neural Network,DPCNN)与堆叠长短时记忆(Stacked Long Short Term Memory,SLSTM)网络的融合模型,旨在提高中文儿童语音情感识别的准确性。通过DPCNN对语音信号中的长距离依赖关系进行提取,再利用SLSTM捕捉情感相关的序列依赖信息,最终通过softmax分类器实现情感状态的判别。实验结果显示,基于DPCNN-SLSTM的模型在中文儿童语音数据集上的情感识别准确率达到了92%,显著优于CNN、LSTM和CNN-LSTM模型。研究结果对于推动儿童语音情感识别技术的发展具有重要意义。
